As AI systems enter into a growing number of societal domains, these systems increasingly
shape and are shaped by user preferences, opinions, and behaviors. However, the design …

We consider a principle or controller that can pick actions from a fixed action set to control an
evolving system with converging dynamics. The actions are interpreted as different …

We consider the problem of learning a realization of a partially observed dynamical system
with linear state transitions and bilinear observations. Under very mild assumptions on the …

The design and evaluation of recommender systems often takes the perspective of
supervised machine learning, treating viewer preferences and the content catalogue as …